X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fio%2FFeaturesFile.java;h=8664cbafe2f501fcfd1492489c5f3c63408eac90;hb=a45774ee31d9f35d4eff46d54d7deab719afb092;hp=943101156c7d38fd1e281181b14e612e956c294e;hpb=bceadbb394604c88ac18e2dcf4b33e735377d7ac;p=jalview.git diff --git a/src/jalview/io/FeaturesFile.java b/src/jalview/io/FeaturesFile.java index 9431011..8664cba 100755 --- a/src/jalview/io/FeaturesFile.java +++ b/src/jalview/io/FeaturesFile.java @@ -1,464 +1,1002 @@ /* -* Jalview - A Sequence Alignment Editor and Viewer -* Copyright (C) 2005 AM Waterhouse, J Procter, G Barton, M Clamp, S Searle -* -* This program is free software; you can redistribute it and/or -* modify it under the terms of the GNU General Public License -* as published by the Free Software Foundation; either version 2 -* of the License, or (at your option) any later version. -* -* This program is distributed in the hope that it will be useful, -* but WITHOUT ANY WARRANTY; without even the implied warranty of -* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -* GNU General Public License for more details. -* -* You should have received a copy of the GNU General Public License -* along with this program; if not, write to the Free Software -* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA -*/ + * Jalview - A Sequence Alignment Editor and Viewer (Version 2.7) + * Copyright (C) 2011 J Procter, AM Waterhouse, G Barton, M Clamp, S Searle + * + * This file is part of Jalview. + * + * Jalview is free software: you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version. + * + * Jalview is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty + * of MERCHANTABILITY or FITNESS FOR A PARTICULAR + * PURPOSE. See the GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License along with Jalview. If not, see . + */ package jalview.io; -import jalview.datamodel.*; - import java.io.*; import java.util.*; -import jalview.schemes.UserColourScheme; +import jalview.analysis.SequenceIdMatcher; +import jalview.datamodel.*; +import jalview.schemes.*; +import jalview.util.Format; /** - * DOCUMENT ME! - * - * @author $author$ + * Parse and create Jalview Features files Detects GFF format features files and + * parses. Does not implement standard print() - call specific printFeatures or + * printGFF. Uses AlignmentI.findSequence(String id) to find the sequence object + * for the features annotation - this normally works on an exact match. + * + * @author AMW * @version $Revision$ */ public class FeaturesFile extends AlignFile { - /** - * Creates a new FeaturesFile object. - */ - public FeaturesFile() - { - } + /** + * work around for GFF interpretation bug where source string becomes + * description rather than a group + */ + private boolean doGffSource = true; + + /** + * Creates a new FeaturesFile object. + */ + public FeaturesFile() + { + } - /** - * Creates a new FeaturesFile object. - * - * @param inStr DOCUMENT ME! - */ - public FeaturesFile(String inStr) - { - super(inStr); - } + /** + * Creates a new FeaturesFile object. + * + * @param inFile + * DOCUMENT ME! + * @param type + * DOCUMENT ME! + * + * @throws IOException + * DOCUMENT ME! + */ + public FeaturesFile(String inFile, String type) throws IOException + { + super(inFile, type); + } - /** - * Creates a new FeaturesFile object. - * - * @param inFile DOCUMENT ME! - * @param type DOCUMENT ME! - * - * @throws IOException DOCUMENT ME! - */ - public FeaturesFile(String inFile, String type) - throws IOException - { - super(inFile, type); - } + public FeaturesFile(FileParse source) throws IOException + { + super(source); + } - /** - * The Application can render HTML, but the applet will - * remove HTML tags and replace links with %LINK% - * Both need to read links in HTML however - * - * @throws IOException DOCUMENT ME! - */ - public boolean parse(AlignmentI align, - Hashtable colours, - boolean removeHTML) - { - return parse(align, colours, null, removeHTML); - } - /** - * The Application can render HTML, but the applet will - * remove HTML tags and replace links with %LINK% - * Both need to read links in HTML however - * - * @throws IOException DOCUMENT ME! - */ - public boolean parse(AlignmentI align, - Hashtable colours, - Hashtable featureLink, - boolean removeHTML) - { - String line = null; - try - { - SequenceI seq = null; - String type, desc, token=null; + /** + * Parse GFF or sequence features file using case-independent matching, discarding URLs + * @param align - alignment/dataset containing sequences that are to be annotated + * @param colours - hashtable to store feature colour definitions + * @param removeHTML - process html strings into plain text + * @return true if features were added + */ + public boolean parse(AlignmentI align, Hashtable colours, + boolean removeHTML) + { + return parse(align, colours, null, removeHTML, false); + } + + /** + * Parse GFF or sequence features file optionally using case-independent matching, discarding URLs + * @param align - alignment/dataset containing sequences that are to be annotated + * @param colours - hashtable to store feature colour definitions + * @param removeHTML - process html strings into plain text + * @param relaxedIdmatching - when true, ID matches to compound sequence IDs are allowed + * @return true if features were added + */ + public boolean parse(AlignmentI align, + Hashtable colours, boolean removeHTML, boolean relaxedIdMatching) + { + return parse(align, colours, null, removeHTML, relaxedIdMatching); + } - int index, start, end; - float score; - StringTokenizer st; - SequenceFeature sf; - String featureGroup = null, groupLink = null; - Hashtable typeLink = new Hashtable(); + /** + * Parse GFF or sequence features file optionally using case-independent matching + * @param align - alignment/dataset containing sequences that are to be annotated + * @param colours - hashtable to store feature colour definitions + * @param featureLink - hashtable to store associated URLs + * @param removeHTML - process html strings into plain text + * @return true if features were added + */ + public boolean parse(AlignmentI align, Hashtable colours, + Hashtable featureLink, boolean removeHTML) + { + return parse(align, colours, featureLink, removeHTML, false); + } - boolean GFFFile = true; + /** + /** + * Parse GFF or sequence features file + * @param align - alignment/dataset containing sequences that are to be annotated + * @param colours - hashtable to store feature colour definitions + * @param featureLink - hashtable to store associated URLs + * @param removeHTML - process html strings into plain text + * @param relaxedIdmatching - when true, ID matches to compound sequence IDs are allowed + * @return true if features were added + */ + public boolean parse(AlignmentI align, + Hashtable colours, Hashtable featureLink, boolean removeHTML, boolean relaxedIdmatching) + { + + String line = null; + try + { + SequenceI seq = null; + String type, desc, token = null; + + int index, start, end; + float score; + StringTokenizer st; + SequenceFeature sf; + String featureGroup = null, groupLink = null; + Hashtable typeLink = new Hashtable(); + /** + * when true, assume GFF style features rather than Jalview style. + */ + boolean GFFFile = true; + while ((line = nextLine()) != null) + { + if (line.startsWith("#")) + { + continue; + } - while ( (line = nextLine()) != null) + st = new StringTokenizer(line, "\t"); + if (st.countTokens() == 1) { - if(line.startsWith("#")) + if (line.trim().equalsIgnoreCase("GFF")) + { + // Start parsing file as if it might be GFF again. + GFFFile = true; continue; - - st = new StringTokenizer(line, "\t"); - if (st.countTokens()>1 && st.countTokens() < 4 ) + } + } + if (st.countTokens() > 1 && st.countTokens() < 4) + { + GFFFile = false; + type = st.nextToken(); + if (type.equalsIgnoreCase("startgroup")) + { + featureGroup = st.nextToken(); + if (st.hasMoreElements()) + { + groupLink = st.nextToken(); + featureLink.put(featureGroup, groupLink); + } + } + else if (type.equalsIgnoreCase("endgroup")) + { + // We should check whether this is the current group, + // but at present theres no way of showing more than 1 group + st.nextToken(); + featureGroup = null; + groupLink = null; + } + else { - GFFFile = false; - type = st.nextToken(); - if (type.equalsIgnoreCase("startgroup")) + Object colour = null; + String colscheme = st.nextToken(); + if (colscheme.indexOf("|") > -1 + || colscheme.trim().equalsIgnoreCase("label")) { - featureGroup = st.nextToken(); - if (st.hasMoreElements()) + // Parse '|' separated graduated colourscheme fields: + // [label|][mincolour|maxcolour|[absolute|]minvalue|maxvalue|thresholdtype|thresholdvalue] + // can either provide 'label' only, first is optional, next two + // colors are required (but may be + // left blank), next is optional, nxt two min/max are required. + // first is either 'label' + // first/second and third are both hexadecimal or word equivalent + // colour. + // next two are values parsed as floats. + // fifth is either 'above','below', or 'none'. + // sixth is a float value and only required when fifth is either + // 'above' or 'below'. + StringTokenizer gcol = new StringTokenizer(colscheme, "|", + true); + // set defaults + int threshtype = AnnotationColourGradient.NO_THRESHOLD; + float min = Float.MIN_VALUE, max = Float.MAX_VALUE, threshval = Float.NaN; + boolean labelCol = false; + // Parse spec line + String mincol = gcol.nextToken(); + if (mincol == "|") { - groupLink = st.nextToken(); - featureLink.put(featureGroup, groupLink); + System.err + .println("Expected either 'label' or a colour specification in the line: " + + line); + continue; + } + String maxcol = null; + if (mincol.toLowerCase().indexOf("label") == 0) + { + labelCol = true; + mincol = (gcol.hasMoreTokens() ? gcol.nextToken() : null); // skip + // '|' + mincol = (gcol.hasMoreTokens() ? gcol.nextToken() : null); + } + String abso = null, minval, maxval; + if (mincol != null) + { + // at least four more tokens + if (mincol.equals("|")) + { + mincol = ""; + } + else + { + gcol.nextToken(); // skip next '|' + } + // continue parsing rest of line + maxcol = gcol.nextToken(); + if (maxcol.equals("|")) + { + maxcol = ""; + } + else + { + gcol.nextToken(); // skip next '|' + } + abso = gcol.nextToken(); + gcol.nextToken(); // skip next '|' + if (abso.toLowerCase().indexOf("abso") != 0) + { + minval = abso; + abso = null; + } + else + { + minval = gcol.nextToken(); + gcol.nextToken(); // skip next '|' + } + maxval = gcol.nextToken(); + if (gcol.hasMoreTokens()) + { + gcol.nextToken(); // skip next '|' + } + try + { + if (minval.length() > 0) + { + min = new Float(minval).floatValue(); + } + } catch (Exception e) + { + System.err + .println("Couldn't parse the minimum value for graduated colour for type (" + + colscheme + + ") - did you misspell 'auto' for the optional automatic colour switch ?"); + e.printStackTrace(); + } + try + { + if (maxval.length() > 0) + { + max = new Float(maxval).floatValue(); + } + } catch (Exception e) + { + System.err + .println("Couldn't parse the maximum value for graduated colour for type (" + + colscheme + ")"); + e.printStackTrace(); + } + } + else + { + // add in some dummy min/max colours for the label-only + // colourscheme. + mincol = "FFFFFF"; + maxcol = "000000"; + } + try + { + colour = new jalview.schemes.GraduatedColor( + new UserColourScheme(mincol).findColour('A'), + new UserColourScheme(maxcol).findColour('A'), min, + max); + } catch (Exception e) + { + System.err + .println("Couldn't parse the graduated colour scheme (" + + colscheme + ")"); + e.printStackTrace(); + } + if (colour != null) + { + ((jalview.schemes.GraduatedColor) colour) + .setColourByLabel(labelCol); + ((jalview.schemes.GraduatedColor) colour) + .setAutoScaled(abso == null); + // add in any additional parameters + String ttype = null, tval = null; + if (gcol.hasMoreTokens()) + { + // threshold type and possibly a threshold value + ttype = gcol.nextToken(); + if (ttype.toLowerCase().startsWith("below")) + { + ((jalview.schemes.GraduatedColor) colour) + .setThreshType(AnnotationColourGradient.BELOW_THRESHOLD); + } + else if (ttype.toLowerCase().startsWith("above")) + { + ((jalview.schemes.GraduatedColor) colour) + .setThreshType(AnnotationColourGradient.ABOVE_THRESHOLD); + } + else + { + ((jalview.schemes.GraduatedColor) colour) + .setThreshType(AnnotationColourGradient.NO_THRESHOLD); + if (!ttype.toLowerCase().startsWith("no")) + { + System.err + .println("Ignoring unrecognised threshold type : " + + ttype); + } + } + } + if (((GraduatedColor) colour).getThreshType() != AnnotationColourGradient.NO_THRESHOLD) + { + try + { + gcol.nextToken(); + tval = gcol.nextToken(); + ((jalview.schemes.GraduatedColor) colour) + .setThresh(new Float(tval).floatValue()); + } catch (Exception e) + { + System.err + .println("Couldn't parse threshold value as a float: (" + + tval + ")"); + e.printStackTrace(); + } + } + // parse the thresh-is-min token ? + if (gcol.hasMoreTokens()) + { + System.err + .println("Ignoring additional tokens in parameters in graduated colour specification\n"); + while (gcol.hasMoreTokens()) + { + System.err.println("|" + gcol.nextToken()); + } + System.err.println("\n"); + } } } - else if (type.equalsIgnoreCase("endgroup")) + else { - //We should check whether this is the current group, - //but at present theres no way of showing more than 1 group - st.nextToken(); - featureGroup = null; - groupLink = null; + UserColourScheme ucs = new UserColourScheme(colscheme); + colour = ucs.findColour('A'); } - else + if (colour != null) { - UserColourScheme ucs = new UserColourScheme(st.nextToken()); - colours.put(type, ucs.findColour("A")); - if (st.hasMoreElements()) + colours.put(type, colour); + } + if (st.hasMoreElements()) + { + String link = st.nextToken(); + typeLink.put(type, link); + if (featureLink == null) { - String link = st.nextToken(); - typeLink.put(type, link); - if(featureLink==null) - featureLink = new Hashtable(); - featureLink.put(type, link); + featureLink = new Hashtable(); } - + featureLink.put(type, link); } - continue; } + continue; + } + String seqId = ""; + while (st.hasMoreElements()) + { - while (st.hasMoreElements()) + if (GFFFile) { - - if(GFFFile) + // Still possible this is an old Jalview file, + // which does not have type colours at the beginning + seqId = token = st.nextToken(); + seq = findName(align, seqId, relaxedIdmatching); + if (seq != null) { - // Still possible this is an old Jalview file, - // which does not have type colours at the beginning - token = st.nextToken(); - seq = align.findName(token); - if(seq != null) + desc = st.nextToken(); + String group = null; + if (doGffSource && desc.indexOf(' ') == -1) { - desc = st.nextToken(); - type = st.nextToken(); - start = Integer.parseInt(st.nextToken()); - end = Integer.parseInt(st.nextToken()); - try + // could also be a source term rather than description line + group = new String(desc); + } + type = st.nextToken(); + try + { + String stt = st.nextToken(); + if (stt.length() == 0 || stt.equals("-")) { - score = Float.parseFloat(st.nextToken()); + start = 0; } - catch (NumberFormatException ex) + else { - score = 0; + start = Integer.parseInt(stt); } - - sf = new SequenceFeature(type, desc, start, end, score, null); - - try + } catch (NumberFormatException ex) + { + start = 0; + } + try + { + String stt = st.nextToken(); + if (stt.length() == 0 || stt.equals("-")) { - sf.setValue("STRAND", st.nextToken()); - sf.setValue("FRAME", st.nextToken()); + end = 0; } - catch (Exception ex) - {} - - seq.getDatasetSequence().addSequenceFeature(sf); - - break; + else + { + end = Integer.parseInt(stt); + } + } catch (NumberFormatException ex) + { + end = 0; + } + // TODO: decide if non positional feature assertion for input data + // where end==0 is generally valid + if (end == 0) + { + // treat as non-positional feature, regardless. + start = 0; + } + try + { + score = new Float(st.nextToken()).floatValue(); + } catch (NumberFormatException ex) + { + score = 0; } - } - - if(GFFFile && seq==null) - { - desc = token; - } - else - desc = st.nextToken(); + sf = new SequenceFeature(type, desc, start, end, score, group); - token = st.nextToken(); - if (!token.equals("ID_NOT_SPECIFIED")) - { - seq = align.findName(token); - st.nextToken(); - } - else - { - try{ - index = Integer.parseInt(st.nextToken()); - seq = align.getSequenceAt(index); + try + { + sf.setValue("STRAND", st.nextToken()); + sf.setValue("FRAME", st.nextToken()); + } catch (Exception ex) + { } - catch(NumberFormatException ex) + + if (st.hasMoreTokens()) { - seq = null; + StringBuffer attributes = new StringBuffer(); + while (st.hasMoreTokens()) + { + attributes.append("\t" + st.nextElement()); + } + // TODO validate and split GFF2 attributes field ? parse out + // ([A-Za-z][A-Za-z0-9_]*) ; and add as + // sf.setValue(attrib, val); + sf.setValue("ATTRIBUTES", attributes.toString()); } - } - if(seq==null) - { - System.out.println("Sequence not found: "+line); + seq.addSequenceFeature(sf); + while ((seq = align.findName(seq, seqId, true)) != null) + { + seq.addSequenceFeature(new SequenceFeature(sf)); + } break; } + } - start = Integer.parseInt(st.nextToken()); - end = Integer.parseInt(st.nextToken()); + if (GFFFile && seq == null) + { + desc = token; + } + else + { + desc = st.nextToken(); + } + if (!st.hasMoreTokens()) + { + System.err + .println("DEBUG: Run out of tokens when trying to identify the destination for the feature.. giving up."); + // in all probability, this isn't a file we understand, so bail + // quietly. + return false; + } - type = st.nextToken(); + token = st.nextToken(); - if (!colours.containsKey(type)) + if (!token.equals("ID_NOT_SPECIFIED")) + { + seq = findName(align, seqId = token, relaxedIdmatching); + st.nextToken(); + } + else + { + seqId = null; + try + { + index = Integer.parseInt(st.nextToken()); + seq = align.getSequenceAt(index); + } catch (NumberFormatException ex) { - // Probably the old style groups file - UserColourScheme ucs = new UserColourScheme(type); - colours.put(type, ucs.findColour("A")); + seq = null; } + } - sf = new SequenceFeature(type, desc, "", start, end, featureGroup); + if (seq == null) + { + System.out.println("Sequence not found: " + line); + break; + } + + start = Integer.parseInt(st.nextToken()); + end = Integer.parseInt(st.nextToken()); - seq.addSequenceFeature(sf); + type = st.nextToken(); - if(groupLink!=null && removeHTML) + if (!colours.containsKey(type)) + { + // Probably the old style groups file + UserColourScheme ucs = new UserColourScheme(type); + colours.put(type, ucs.findColour('A')); + } + sf = new SequenceFeature(type, desc, "", start, end, featureGroup); + if (st.hasMoreTokens()) + { + try { - sf.addLink(groupLink); - sf.description += "%LINK%"; - } - if(typeLink.containsKey(type) && removeHTML) + score = new Float(st.nextToken()).floatValue(); + // update colourgradient bounds if allowed to + } catch (NumberFormatException ex) { - sf.addLink(typeLink.get(type).toString()); - sf.description += "%LINK%"; + score = 0; } + sf.setScore(score); + } + if (groupLink != null && removeHTML) + { + sf.addLink(groupLink); + sf.description += "%LINK%"; + } + if (typeLink.containsKey(type) && removeHTML) + { + sf.addLink(typeLink.get(type).toString()); + sf.description += "%LINK%"; + } + + parseDescriptionHTML(sf, removeHTML); - parseDescriptionHTML(sf, removeHTML); + seq.addSequenceFeature(sf); - //If we got here, its not a GFFFile - GFFFile = false; + while (seqId != null + && (seq = align.findName(seq, seqId, false)) != null) + { + seq.addSequenceFeature(new SequenceFeature(sf)); } + // If we got here, its not a GFFFile + GFFFile = false; } } - catch (Exception ex) + resetMatcher(); + } catch (Exception ex) + { + System.out.println(line); + System.out.println("Error parsing feature file: " + ex + "\n" + line); + ex.printStackTrace(System.err); + resetMatcher(); + return false; + } + + return true; + } + + private AlignmentI lastmatchedAl = null; + + private SequenceIdMatcher matcher = null; + + /** + * clear any temporary handles used to speed up ID matching + */ + private void resetMatcher() + { + lastmatchedAl = null; + matcher = null; + } + + private SequenceI findName(AlignmentI align, String seqId, + boolean relaxedIdMatching) + { + SequenceI match = null; + if (relaxedIdMatching) + { + if (lastmatchedAl != align) { - System.out.println(line); - ex.printStackTrace(); - System.out.println("Error parsing feature file: " + ex +"\n"+line); - return false; + matcher = new SequenceIdMatcher( + (lastmatchedAl = align).getSequencesArray()); } + match = matcher.findIdMatch(seqId); + } + else + { + match = align.findName(seqId, true); + } + return match; + } - return true; + public void parseDescriptionHTML(SequenceFeature sf, boolean removeHTML) + { + if (sf.getDescription() == null) + { + return; } + jalview.util.ParseHtmlBodyAndLinks parsed = new jalview.util.ParseHtmlBodyAndLinks(sf.getDescription(), removeHTML, newline); - void parseDescriptionHTML(SequenceFeature sf, boolean removeHTML) + sf.description = (removeHTML) ? parsed.getNonHtmlContent() : sf.description; + for (String link:parsed.getLinks()) { - StringBuffer sb = new StringBuffer(); - StringTokenizer st = new StringTokenizer(sf.getDescription(), "<"); - String token, link; - while(st.hasMoreElements()) - { - token = st.nextToken("<>"); - if(token.equalsIgnoreCase("html") || token.startsWith("/")) - continue; + sf.addLink(link); + } - if(token.startsWith("a href=")) - { - link = token.substring(token.indexOf("\"")+1, token.length()-1); - String label = st.nextToken("<>"); - sf.addLink(label+"|"+link); - sb.append(label+"%LINK%"); - } - else if(token.equalsIgnoreCase("br")) - sb.append("\n"); - else - sb.append(token); - } + } - if(removeHTML) - sf.description = sb.toString(); + /** + * generate a features file for seqs includes non-pos features by default. + * + * @param seqs + * source of sequence features + * @param visible + * hash of feature types and colours + * @return features file contents + */ + public String printJalviewFormat(SequenceI[] seqs, Hashtable visible) + { + return printJalviewFormat(seqs, visible, true, true); } - /** - * DOCUMENT ME! - * - * @param s DOCUMENT ME! - * @param len DOCUMENT ME! - * @param gaps DOCUMENT ME! - * @param displayId DOCUMENT ME! - * - * @return DOCUMENT ME! - */ - public String printJalviewFormat(SequenceI [] seqs, - Hashtable visible) + /** + * generate a features file for seqs with colours from visible (if any) + * + * @param seqs + * source of features + * @param visible + * hash of Colours for each feature type + * @param visOnly + * when true only feature types in 'visible' will be output + * @param nonpos + * indicates if non-positional features should be output (regardless + * of group or type) + * @return features file contents + */ + public String printJalviewFormat(SequenceI[] seqs, Hashtable visible, + boolean visOnly, boolean nonpos) + { + StringBuffer out = new StringBuffer(); + SequenceFeature[] next; + boolean featuresGen = false; + if (visOnly && !nonpos && (visible == null || visible.size() < 1)) { - StringBuffer out = new StringBuffer(); - SequenceFeature [] next; - - if(visible==null || visible.size()<1) - return "No Features Visible"; - - Enumeration en = visible.keys(); - String type; - int color; - while( en.hasMoreElements() ) - { - type = en.nextElement().toString(); - color = Integer.parseInt( visible.get(type).toString() ); - out.append(type + "\t" - + jalview.util.Format.getHexString( - new java.awt.Color(color) ) - +"\n"); - } + // no point continuing. + return "No Features Visible"; + } - //Work out which groups are both present and visible - Vector groups = new Vector(); - int groupIndex = 0; + if (visible != null && visOnly) + { + // write feature colours only if we're given them and we are generating + // viewed features + // TODO: decide if feature links should also be written here ? + Enumeration en = visible.keys(); + String type, color; + while (en.hasMoreElements()) + { + type = en.nextElement().toString(); - for(int i=0; i 0 && groupIndex < groups.size()) + if (next[j].featureGroup != null + && !groups.contains(next[j].featureGroup)) { - group = groups.elementAt(groupIndex).toString(); - out.append("\nSTARTGROUP\t" + group + "\n"); + groups.addElement(next[j].featureGroup); } - else - group = null; + } + } + } + + String group = null; + do + { + + if (groups.size() > 0 && groupIndex < groups.size()) + { + group = groups.elementAt(groupIndex).toString(); + out.append(newline); + out.append("STARTGROUP\t"); + out.append(group); + out.append(newline); + } + else + { + group = null; + } - for (int i = 0; i < seqs.length; i++) + for (int i = 0; i < seqs.length; i++) + { + next = seqs[i].getSequenceFeatures(); + if (next != null) + { + for (int j = 0; j < next.length; j++) { - next = seqs[i].getSequenceFeatures(); - if (next != null) + isnonpos = next[j].begin == 0 && next[j].end == 0; + if ((!nonpos && isnonpos) + || (!isnonpos && visOnly && !visible + .containsKey(next[j].type))) { - for (int j = 0; j < next.length; j++) - { - if (!visible.containsKey(next[j].type)) - continue; + // skip if feature is nonpos and we ignore them or if we only + // output visible and it isn't non-pos and it's not visible + continue; + } - if (group != null - && (next[j].featureGroup==null - || !next[j].featureGroup.equals(group)) - ) - continue; + if (group != null + && (next[j].featureGroup == null || !next[j].featureGroup + .equals(group))) + { + continue; + } - if(group==null && next[j].featureGroup!=null) - continue; + if (group == null && next[j].featureGroup != null) + { + continue; + } + // we have features to output + featuresGen = true; + if (next[j].description == null + || next[j].description.equals("")) + { + out.append(next[j].type + "\t"); + } + else + { + if (next[j].links != null + && next[j].getDescription().indexOf("") == -1) + { + out.append(""); + } - if(next[j].description==null || next[j].description.equals("")) - out.append(next[j].type+"\t"); - else - out.append(next[j].description + "\t"); + out.append(next[j].description + " "); + if (next[j].links != null) + { + for (int l = 0; l < next[j].links.size(); l++) + { + String label = next[j].links.elementAt(l).toString(); + String href = label.substring(label.indexOf("|") + 1); + label = label.substring(0, label.indexOf("|")); + + if (next[j].description.indexOf(href) == -1) + { + out.append("" + label + ""); + } + } - out.append( seqs[i].getName() + "\t-1\t" - + next[j].begin + "\t" - + next[j].end + "\t" - + next[j].type + "\n" - ); + if (next[j].getDescription().indexOf("") == -1) + { + out.append(""); + } } - } - } - if(group!=null) - { - out.append("ENDGROUP\t"+group+"\n"); - groupIndex++; + out.append("\t"); + } + out.append(seqs[i].getName()); + out.append("\t-1\t"); + out.append(next[j].begin); + out.append("\t"); + out.append(next[j].end); + out.append("\t"); + out.append(next[j].type); + if (next[j].score != Float.NaN) + { + out.append("\t"); + out.append(next[j].score); + } + out.append(newline); } - else - break; - } - while(groupIndex < groups.size()+1); + } + if (group != null) + { + out.append("ENDGROUP\t"); + out.append(group); + out.append(newline); + groupIndex++; + } + else + { + break; + } - return out.toString(); - } + } while (groupIndex < groups.size() + 1); - public String printGFFFormat(SequenceI [] seqs, Hashtable visible) + if (!featuresGen) { - StringBuffer out = new StringBuffer(); - SequenceFeature [] next; + return "No Features Visible"; + } + + return out.toString(); + } + + /** + * generate a gff file for sequence features includes non-pos features by + * default. + * + * @param seqs + * @param visible + * @return + */ + public String printGFFFormat(SequenceI[] seqs, Hashtable visible) + { + return printGFFFormat(seqs, visible, true, true); + } - for(int i=0; i